interview-coach
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill implements persistent state management by reading and writing to a dedicated configuration directory (
~/.interview-coach/) within the user's home directory. This is used to maintain a personalized learning progress file (progress.md) containing ability metrics and review schedules. - [DATA_EXFILTRATION]: The skill utilizes a search tool (
anysearch) to retrieve current interview experiences from external web sources. This is a functional requirement to keep the question bank updated with the latest industry trends. - [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection via external search results.
- Ingestion points: Data retrieved from the
anysearchtool in the 'Question Sourcing' step (SKILL.md, Section B.2). - Boundary markers: The instructions do not specify the use of delimiters or warnings when processing search results.
- Capability inventory: The skill possesses file-system read/write capabilities for its progress tracking and search execution capabilities.
- Sanitization: No specific filtering or validation logic is defined for the external content before it is processed by the agent.
Audit Metadata